Skip to content

Fix use_lu_lambdas and use_karras_sigmas with beta_schedule=squaredcos_cap_v2 in DPMSolverMultistepScheduler #10740

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 5 commits into from
Feb 12, 2025
Merged

Fix use_lu_lambdas and use_karras_sigmas with beta_schedule=squaredcos_cap_v2 in DPMSolverMultistepScheduler #10740

Changes from all commits
Commits
Show all changes
5 commits
Select commit Hold shift + click to select a range
acbe140
Fix `use_lu_lambdas` and `use_karras_sigmas` with `beta_schedule=squa…
hlky Feb 6, 2025
6544e47
round if linear or scaled_linear
hlky Feb 7, 2025
1671537
Update scheduling_dpmsolver_multistep.py
hlky Feb 12, 2025
c438ad4
Update scheduling_dpmsolver_multistep.py
hlky Feb 12, 2025
1c2a3c7
Update scheduling_dpmsolver_multistep.py
hlky Feb 12, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
8 changes: 6 additions & 2 deletions src/diffusers/schedulers/scheduling_dpmsolver_multistep.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -399,12 +399,16 @@ def set_timesteps(
if self.config.use_karras_sigmas:
sigmas = np.flip(sigmas).copy()
sigmas = self._convert_to_karras(in_sigmas=sigmas, num_inference_steps=num_inference_steps)
timesteps = np.array([self._sigma_to_t(sigma, log_sigmas) for sigma in sigmas]).round()
timesteps = np.array([self._sigma_to_t(sigma, log_sigmas) for sigma in sigmas])
if self.config.beta_schedule != "squaredcos_cap_v2":
timesteps = timesteps.round()
elif self.config.use_lu_lambdas:
lambdas = np.flip(log_sigmas.copy())
lambdas = self._convert_to_lu(in_lambdas=lambdas, num_inference_steps=num_inference_steps)
sigmas = np.exp(lambdas)
timesteps = np.array([self._sigma_to_t(sigma, log_sigmas) for sigma in sigmas]).round()
timesteps = np.array([self._sigma_to_t(sigma, log_sigmas) for sigma in sigmas])
if self.config.beta_schedule != "squaredcos_cap_v2":
timesteps = timesteps.round()
elif self.config.use_exponential_sigmas:
sigmas = np.flip(sigmas).copy()
sigmas = self._convert_to_exponential(in_sigmas=sigmas, num_inference_steps=num_inference_steps)
Expand Down